Patents Examined by Aaron W Carter
  • Patent number: 10817710
    Abstract: Predictive theft notifications are used to coordinate appropriate responses to persons who are likely to commit acts of theft. Image data is generated and processed in a computer processing device to recognize the presence of a facial image comprising a face of a person. An analysis is performed of data representative of the facial image to determine a biometric match relative to one or more biometric models of facial images stored in a database. Based on this analysis, at least one predictive notification is generated with regard to a future potential theft of merchandise from the secured facility. The predictive notification is generated based upon a determination of the biometric match.
    Type: Grant
    Filed: June 12, 2018
    Date of Patent: October 27, 2020
    Assignee: SENSORMATIC ELECTRONICS, LLC
    Inventors: Manjuprakash R. Rao, Surajit Borah, Hubert A. Patterson
  • Patent number: 10818042
    Abstract: An image information overlay system retrieves an image associated with a vehicle listing and uses machine learning models to classify the image, generating identification data that may comprise a vehicle make and model, a feature or part of the vehicle present in the image, and a location of the vehicle feature or part. The identification data or an individual identifier of the vehicle, such as a Vehicle Identification Number (VIN), may be used to retrieve overlay information related to the vehicle make and model, such as recalls or known maintenance issues or information specific to the vehicle, such as mileage, accident reports, or ownership history. The overlay information is displayed on the image as an overlay at the location of the vehicle feature or part corresponding to the overlay information.
    Type: Grant
    Filed: January 14, 2020
    Date of Patent: October 27, 2020
    Assignee: Capital One Services, LLC
    Inventors: Qiaochu Tang, Geoffrey Dagley, Micah Price, Avid Ghamsari, Jason Richard Hoover
  • Patent number: 10803351
    Abstract: In a case where generating a training image of an object to be used to generate a dictionary to be referred to in image recognition processing of detecting the object from an input image, model information of an object to be detected is set, and a luminance image of the object and a range image are input. The luminance distribution of the surface of the object is estimated based on the luminance image and the range image, and the training image of the object is generated based on the model information and the luminance distribution.
    Type: Grant
    Filed: December 10, 2018
    Date of Patent: October 13, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventor: Masato Aoba
  • Patent number: 10796413
    Abstract: In a video monitoring system including HD and SD cameras, the system includes, on the transmitting side, a division/rotation processing unit for dividing an SD image into multiple divided images horizontally and performing a process for rotating the divided images by 90 degrees to the left, an image insertion unit for arranging and superimposing the divided images in a text telop region of an HD image, and a HD encoder for compressing and transmitting the HD image with the SD image superimposed. The system further includes, on the receiving side, a HD decoder for expanding the received HD image, and an output image processing unit for extracting the multiple divided images of the SD image and rotating these images by 90 degrees to the right, sorting and combining these images to reproduce the SD image, and outputting the expanded output HD image and the reproduced output SD image.
    Type: Grant
    Filed: August 30, 2017
    Date of Patent: October 6, 2020
    Assignee: HITACHI KOKUSAI ELECTRIC INC.
    Inventor: Tadamichi Kudo
  • Patent number: 10796193
    Abstract: A computer implemented method to present digital images may include storing a digital image in a database and applying a digital image processing technique to the digital image to identify a region of interest of the digital image. The method may also include storing region data that identifies the region of interest of the digital image in the database and receiving a request for information associated with the digital image from a digital device. In response to the request, the method may include providing the digital image and the region data for transmission to the digital device, the digital device configured to adjust a cropping view of the digital image based on the region data to display the region of interest of the digital image.
    Type: Grant
    Filed: January 5, 2018
    Date of Patent: October 6, 2020
    Assignee: eBay Inc.
    Inventors: Susan Stieglitz, Yem Huynh, Fazeel Mufti
  • Patent number: 10783356
    Abstract: Aspects differentially drive the graphic display of links overlaid between people in a group photograph as a function of associated relationship type. Individuals are distinguished within the photograph and relationships are identified among the individuals that differ from one another with respect to type of relationship, by extracting relationship data via natural language processing relative to social network data of one or more of the identified individuals. Thus, a graphic display device is driven to display the identified relationships via each of different overlay elements that are depicted directly on the photograph, link respective ones of the identified individuals, and use different graphic elements to convey differences in respective types of the relationships that are determined among the identified individuals.
    Type: Grant
    Filed: November 4, 2019
    Date of Patent: September 22, 2020
    Assignee: International Business Machines Corporation
    Inventors: James E. Bostick, John M. Ganci, Jr., Sarbajit K. Rakshit, Kimberly G. Starks
  • Patent number: 10776673
    Abstract: A method for training a CNN by using a camera and a radar together, to thereby allow the CNN to perform properly even when an object depiction ratio of a photographed image acquired through the camera is low due to a bad condition of a photographing circumstance is provided. And the method includes steps of: (a) a learning device instructing a convolutional layer to apply a convolutional operation to a multichannel integrated image, to thereby generate a feature map; (b) the learning device instructing an output layer to apply an output operation to the feature map, to thereby generate estimated object information; and (c) the learning device instructing a loss layer to generate a loss by using the estimated object information and GT object information corresponding thereto, and to perform backpropagation by using the loss, to thereby learn at least part of parameters in the CNN.
    Type: Grant
    Filed: December 31, 2019
    Date of Patent: September 15, 2020
    Assignee: Stradvision, Inc.
    Inventors: Kye-Hyeon Kim, Yongjoong Kim, Hak-Kyoung Kim, Woonhyun Nam, SukHoon Boo, Myungchul Sung, Dongsoo Shin, Donghun Yeo, Wooju Ryu, Myeong-Chun Lee, Hyungsoo Lee, Taewoong Jang, Kyungjoong Jeong, Hongmo Je, Hojin Cho
  • Patent number: 10776111
    Abstract: A point cloud rendering method and apparatus for real-time point cloud data collection from a variety of sensor types is provided that delivers enhanced performance including reducing processing requirements, limiting local memory consumption and optimizing overall data visualization.
    Type: Grant
    Filed: May 24, 2018
    Date of Patent: September 15, 2020
    Assignee: Topcon Positioning Systems, Inc.
    Inventors: Ivan Charamisinau, Michael Burenkov, Dmitry Datko
  • Patent number: 10762337
    Abstract: Training a generative adversarial network (GAN) for use in facial recognition, comprising providing an input image of a particular face into a facial recognition system to obtain a faceprint; obtaining, based on the input faceprint and a noise value, a set of output images from a GAN generator; obtaining feedback from a GAN discriminator, wherein obtaining feedback comprises inputting each output image into the GAN discriminator and determining a set of likelihood values indicative of whether each output image comprises a facial image; determining, based on each output image, a modified noise value; inputting each output image into a second facial recognition network to determine a set of modified faceprints; defining, based on each modified noise value and modified faceprint, feedback for the GAN generator, wherein the feedback comprises a first value and a second value; and modifying control parameters of the GAN generator.
    Type: Grant
    Filed: May 30, 2018
    Date of Patent: September 1, 2020
    Assignee: Apple Inc.
    Inventors: Vinay Sharma, Yaozong Gao
  • Patent number: 10762616
    Abstract: Systems and methods described herein are directed to changing models and analytics algorithms on an edge node from a core server, which can be useful in situations such as optimized factories when the edge node is physically close to data sources such as within a factory plant. The core server or cloud runs analytics algorithms and models concurrently with data received from edge nodes, and replaces the edge node with more accurate analytics algorithms and models as applicable.
    Type: Grant
    Filed: July 9, 2018
    Date of Patent: September 1, 2020
    Assignee: Hitachi, Ltd.
    Inventor: Daisuke Ito
  • Patent number: 10755387
    Abstract: A method for determining whether a pixel of a computer-rendered image is a firefly includes: dividing a plurality of samples originating from the pixel, into first and second subsets; identifying whether the pixel is an outlier based on variance data of the first subset; identifying whether the pixel is an outlier based on variance data of the second subset. The pixel is determined as not a firefly in response to both the pixel being identified as an outlier based on the variance data of the first subset, and the pixel being identified as an outlier based on the variance data of the second subset. The pixel is determined as a firefly in response to the pixel being not identified as an outlier based on the variance data of the first (second) subset and being identified as an outlier based on the variance data of the second (first) subset.
    Type: Grant
    Filed: December 31, 2018
    Date of Patent: August 25, 2020
    Assignee: DreamWorks Animation LLC
    Inventor: Keith Ralph Jeffery
  • Patent number: 10755120
    Abstract: Embodiments of the present invention provide an end-to-end lightweight method and apparatus for license plate recognition. The method comprises: obtaining an image to be recognized; obtaining a number of a license plate in the image to be recognized and position coordinates of the license plate in the image to be recognized on the basis of the image to be recognized and a pre-trained target license plate recognition model, wherein the target license plate recognition model comprises a target feature extraction network, a target region candidate localization network, a target super-resolution generation network and a target recurrent neural network. Because in this solution, once an image to be recognized is input into the target license plate recognition model, the target license plate recognition model can output the license plate number and position coordinates of the license plate in the image to be recognized, one realizes an end-to-end model.
    Type: Grant
    Filed: September 19, 2018
    Date of Patent: August 25, 2020
    Assignee: BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS
    Inventors: Huiyuan Fu, Huadong Ma, Yifan Zhang, Yu Cao, Dengkui Zhang
  • Patent number: 10750206
    Abstract: A method for encoding at least one image split into blocks. The method includes, for a current block to be encoded from the image, at least one modification of two data points in the block via an operation of linear combinations operating on the two data points, at the end of which a modified block is obtained, application of a separable transform operation to the data points in the modified block, and encoding the data points obtained after application of the separable transform operation.
    Type: Grant
    Filed: November 29, 2016
    Date of Patent: August 18, 2020
    Assignee: ORANGE
    Inventors: Adria Arrufat, Pierrick Philippe
  • Patent number: 10747971
    Abstract: A method for identification (ID) verification using a device with embedded radio-frequency identification (RFID) functionality is disclosed. The method comprises capturing, by a camera associated with a client device, an image of an ID document having an embedded RFID chip. The image is transmitted to a server for optical character recognition to extract and recognize printed data associated with the ID document. The client device can receive the printed data from the server and use the printed data to unlock the RFID chip by an RFID reader. Digital data associated with the ID document can be retrieved from the RFID chip and compared to the printed data. If the digital data and the printed data match, the ID document is verified. Otherwise, the ID document is rejected.
    Type: Grant
    Filed: August 1, 2019
    Date of Patent: August 18, 2020
    Assignee: IDchecker, Inc.
    Inventor: Michael Hagen
  • Patent number: 10733511
    Abstract: A learning method for selecting specific information, to be used for updating an HD Map is provided. And the method includes steps of: (a) a learning device instructing a coordinate neural network to generate a local feature map and a global feature vector by applying a coordinate neural network operation to a coordinate matrix; (b) the learning device instructing a determination neural network to generate a first estimated suitability score to an N-th estimated suitability score by applying a determination neural network operation to the integrated feature map; (c) the learning device instructing a loss layer to generate a loss by referring to (i) the first estimated suitability score to the N-th estimated suitability score and (ii) a first Ground Truth(GT) suitability score to an N-th GT suitability score, and perform backpropagation by using the loss, to thereby learn parameters of the determination neural network and the coordinate neural network.
    Type: Grant
    Filed: December 23, 2019
    Date of Patent: August 4, 2020
    Assignee: StradVision, Inc.
    Inventors: Kye-Hyeon Kim, Yongjoong Kim, Hak-Kyoung Kim, Woonhyun Nam, SukHoon Boo, Myungchul Sung, Dongsoo Shin, Donghun Yeo, Wooju Ryu, Myeong-Chun Lee, Hyungsoo Lee, Taewoong Jang, Kyungjoong Jeong, Hongmo Je, Hojin Cho
  • Patent number: 10732123
    Abstract: Various techniques are disclosed to provide a cloud-based, networked infrared (IR) inspection routing system that provides a user interface for remotely defining an inspection routing workflow for an inspection of a site, and provides an IR camera that presents customized and context-aware instructions to an on-site inspector to perform the inspection. The IR camera may be further configured to analyze IR images that are captured during the inspection and provides additional guidance in response to the analysis of the captured IR images according to the defined inspection routing workflow.
    Type: Grant
    Filed: May 30, 2018
    Date of Patent: August 4, 2020
    Assignee: FLIR SYSTEMS AB
    Inventors: Mats Ahlstrom, Kent Wickenberg, Tintin Razavian
  • Patent number: 10728461
    Abstract: A method for correcting an incorrect angle of a camera is provided. And the method includes steps of: (a) a computing device, generating first reference data or second reference data according to circumstance information by referring to a reference image; (b) the computing device generating a first angle error or a second angle error by referring to the first reference data or the second reference data with vehicle coordinate data; and (c) the computing device instructing a physical rotation module to adjust the incorrect angle by referring to the first angle error or the second angle error.
    Type: Grant
    Filed: January 10, 2020
    Date of Patent: July 28, 2020
    Assignee: Stradvision, Inc.
    Inventors: Kye-Hyeon Kim, Yongjoong Kim, Hak-Kyoung Kim, Woonhyun Nam, SukHoon Boo, Myungchul Sung, Dongsoo Shin, Donghun Yeo, Wooju Ryu, Myeong-Chun Lee, Hyungsoo Lee, Taewoong Jang, Kyungjoong Jeong, Hongmo Je, Hojin Cho
  • Patent number: 10728559
    Abstract: An apparatus configured to process video data includes a memory and a processor in communication with the memory where the processor is configured to obtain an input picture including a color component having a first color characteristic, obtain a plurality of parameters associated with the color component of at least one sample of the input picture where the plurality of parameters are indicative of pivot points associated with a piece-wise linear function associated with the color component, determine that a value of at least one parameter of the plurality of parameters includes a negative value, apply, on the at least one sample of the input picture, the piece-wise linear function defined with the at least one parameter having a negative value, generate at least one output sample of an output picture including the color component having a second color characteristic based on the application of the piece-wise linear function.
    Type: Grant
    Filed: July 5, 2018
    Date of Patent: July 28, 2020
    Assignee: Qualcomm Incorporated
    Inventors: Adarsh Krishnan Ramasubramonian, Joel Sole Rojals, Dmytro Rusanovskyy
  • Patent number: 10719731
    Abstract: Techniques are provided that include identifying robust features within a training image. Training features are generated by applying a feature detection algorithm to the training image, each training feature having a training feature location within the training image. At least a portion of the training image is transformed into a transformed image in accordance with a predefined image transformation. Transform features are generated by applying the feature detection algorithm to the transformed image, each transform feature having a transform feature location within the transformed image.
    Type: Grant
    Filed: June 24, 2019
    Date of Patent: July 21, 2020
    Assignee: Nant Holdings IP, LLC
    Inventors: Bing Song, Liwen Lin, Mustafa Jaber
  • Patent number: 10713782
    Abstract: Disclosed are systems, devices, and methods for detecting characteristics of an unhatched egg. A set of images of an unhatched egg are obtained, where each of the spectral images is obtained in a particular wavelength range. The set of images is processed to extract image features, where the image features includes an image texture feature. The extracted image features are processed to classify the unhatched egg according to at least one characteristic. The at least one characteristic may include fertility and/or gender.
    Type: Grant
    Filed: February 17, 2016
    Date of Patent: July 14, 2020
    Assignee: MATRIXSPEC SOLUTIONS INC.
    Inventors: Michael Ngadi, Li Liu, Chen Zheng